作者位次 #3/10ACL 2026Findings· Findings of ACL
Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval-Augmented Generation
Ekaterina Fadeeva · Aleksandr Rubashevskii · Dzianis Piatrashyn · Roman Vashurin · Shehzaad Dhuliawala · Artem Shelmanov · Timothy Baldwin · Preslav Nakov · Mrinmaya Sachan · Maxim Panov
摘要
Large Language Models (LLMs) enhanced with knowledge retrieval, an approach known as Retrieval-Augmented Generation (RAG), have achieved strong performance in open-domain question answering. However, RAG remains prone to hallucinations: factually incorrect outputs may arise from inaccuracies in t...